x Turn on thread page Beta
 You are Here: Home >< Maths

SD Help watch

1. I'm writing an essay and came across a paper I want to use. The paper contains the following data:

"Telomere length was significantly shorter in lung cancer patients than in controls (mean ± standard deviation: 1.59 ± 0.75 versus 2.16 ± 1.10, P < 0.0001"

They suggest that there is a significant difference between the control and the experimental group, but the SDs of the two groups overlap. Does this mean that the data are not significantly different, or am I confusing SD with SE?
2. (Original post by thenumber2goose)
I'm writing an essay and came across a paper I want to use. The paper contains the following data:

"Telomere length was significantly shorter in lung cancer patients than in controls (mean ± standard deviation: 1.59 ± 0.75 versus 2.16 ± 1.10, P < 0.0001"

They suggest that there is a significant difference between the control and the experimental group, but the SDs of the two groups overlap. Does this mean that the data are not significantly different, or am I confusing SD with SE?

Not an expert on this, but I suspect the significance is dependent on the size of the groups.
E.g. Just one patient having a length of 2.16 compared with 1.59 is not significant. But if 100 do, then it is.

A proper analysis is beyond my knowledge base, but there are others on here who may be able to shed more light on it.
3. (Original post by thenumber2goose)
I'm writing an essay and came across a paper I want to use. The paper contains the following data:

"Telomere length was significantly shorter in lung cancer patients than in controls (mean ± standard deviation: 1.59 ± 0.75 versus 2.16 ± 1.10, P < 0.0001"

They suggest that there is a significant difference between the control and the experimental group, but the SDs of the two groups overlap. Does this mean that the data are not significantly different, or am I confusing SD with SE?
If you picked 101 patients from your control group and averaged their length, the expected average (mean) of the sample would be 2.16. If you did that lots of times, you would not get exactly 2.16 every time - it would fluctuate. The sample mean would be normally distributed with a mean of 2.16 and a standard deviation of 0.11 - one tenth of the individual variation. ( 1/sqrt(101 -1) ).

So if your 101 cancer patients turned up with a mean of 1.59 you would say wow! That's very low. It's very unlikely that this is just like the control group.
4. (Original post by thenumber2goose)
I'm writing an essay and came across a paper I want to use. The paper contains the following data:

"Telomere length was significantly shorter in lung cancer patients than in controls (mean ± standard deviation: 1.59 ± 0.75 versus 2.16 ± 1.10, P < 0.0001"

They suggest that there is a significant difference between the control and the experimental group, but the SDs of the two groups overlap. Does this mean that the data are not significantly different, or am I confusing SD with SE?
You've answered your own question; yes, this confuses the observed standard deviation of the samples with the standard error of the mean, the latter being the basis for the statistical test,
5. Great, thanks for the replies

TSR Support Team

We have a brilliant team of more than 60 Support Team members looking after discussions on The Student Room, helping to make it a fun, safe and useful place to hang out.

This forum is supported by:
Updated: October 21, 2015
Today on TSR

Unconditional offer...

But going to get a U!

Poll
Useful resources

Maths Forum posting guidelines

Not sure where to post? Read the updated guidelines here

How to use LaTex

Writing equations the easy way

Study habits of A* students

Top tips from students who have already aced their exams

Chat with other maths applicants